CN118348943B - Industrial equipment intelligent scheduling system and method based on self-adaptive control - Google Patents

Abstract

The invention discloses an intelligent dispatching system and method for industrial equipment based on self-adaptive control, and belongs to the technical field of intelligent dispatching of industrial equipment. The system of the invention comprises: the system comprises a data acquisition and processing module, an industrial equipment association index calculation module, a load condition evaluation and comparison module, a maintenance and scheduling decision module and a maintenance management and execution module; the intelligent scheduling of the industrial equipment is realized by utilizing data acquisition, association index calculation and load evaluation; the maintenance and scheduling decision module ensures the stable operation of the production line through real-time scheduling decision, and the maintenance management and execution module is responsible for maintenance and task scheduling, so that the production efficiency and the equipment utilization rate are improved, and the industrial intelligent development is promoted. The invention can be widely applied to the fields of manufacturing industry and the like, improves the production efficiency and the resource utilization efficiency, and promotes the intelligent level improvement of industrial production.

Description

An industrial equipment intelligent scheduling system and method based on adaptive control

Technical Field

The present invention relates to the technical field of intelligent scheduling of industrial equipment, and in particular to an intelligent scheduling system and method for industrial equipment based on adaptive control.

Background Art

As the degree of automation in industrial production continues to increase, the number and complexity of equipment in factories are also increasing rapidly. Modern factories often contain a large number of mechanical equipment, production lines, and automation systems, and there are complex connections and interactions between these devices. Traditional industrial equipment scheduling systems usually use pre-defined static rules or simple plans to allocate tasks and resources. However, these methods are difficult to adapt to the rapidly changing production environment and task requirements.

Although some existing industrial equipment scheduling systems can achieve automated control, they still have shortcomings in practical applications. For example, when an industrial equipment on a production line fails and there is currently no replacement for the failed industrial equipment, the existing industrial equipment scheduling system will sometimes determine whether other production lines can be combined into a temporary production line to replace the failed production line based on the equipment models of the production line; but this method requires a lot of time and effort, especially when the production line is complex, which may cause the production line to be down for too long, affecting production efficiency.

Summary of the invention

The purpose of the present invention is to provide an industrial equipment intelligent scheduling system and method based on adaptive control to solve the problems raised in the above background technology.

In order to solve the above technical problems, the present invention provides the following technical solutions:

According to the above description, the industrial equipment intelligent scheduling system based on adaptive control includes the following modules and their functional units:

An industrial equipment intelligent scheduling method based on adaptive control comprises the following steps:

Step S100. Obtain the industrial equipment information and corresponding historical production data of all production lines in the production workshop to form a production line industrial equipment set; based on the production line industrial equipment set, obtain the corresponding industrial equipment information of each production line, thereby obtaining the correlation index of the industrial equipment model;

Step S200. Based on the historical production data of the production workshop, the load condition of the industrial equipment of each production line is evaluated; the load condition evaluation result of the industrial equipment of each production line is matched with the correlation index of the industrial equipment model, thereby forming a control data set;

Step S300. Obtain the real-time production data of the production workshop, and calculate the real-time load evaluation of the industrial equipment of each production line based on the real-time production data of the production workshop; for each production line, determine whether the current industrial equipment needs maintenance based on the real-time load evaluation results of the industrial equipment and in combination with the reference data set;

Step S400. For the production line where the industrial equipment that needs maintenance is located, shut down the industrial equipment that currently needs maintenance, compare the remaining industrial equipment on the production line with the industrial equipment on other production lines, and determine whether there is a production line composed of the same industrial equipment; obtain real-time information on pending production tasks. If other production lines have completed all real-time pending production tasks, determine whether there are other production lines that form a temporary production line to replace the production line where the industrial equipment that needs maintenance is located, and make intelligent scheduling decisions based on the judgment results.

Furthermore, step S100 includes:

S101. The industrial equipment information includes the industrial equipment number and the industrial equipment distribution location, and the industrial equipment number includes the industrial equipment model; the historical production data refers to the production data of the production workshop in the past period of time, including the production task execution data, operation data and maintenance records of each industrial equipment;

S102. For each production line in the production workshop, extract the corresponding industrial equipment number, and set a position coordinate according to the corresponding industrial equipment distribution position, and correspond the position coordinate with the industrial equipment number, so as to form a production line industrial equipment set Ai, and Ai={ai1,ai2,...,ain}, where i represents the production line number, ai1 represents the industrial equipment number with the position coordinate (i,1), and (i,1) represents the position coordinate of the industrial equipment in the i-th row and the first column; ai2 represents the industrial equipment number with the position coordinate (i,2), and so on, ain represents the industrial equipment number with the position coordinate (i,n), and n represents the number of industrial equipment constituting the production line;

S103. Draw a correlation map of the industrial equipment corresponding to each production line based on the set of production line industrial equipment corresponding to each production line, wherein each industrial equipment corresponds to one correlation map; integrate the correlation maps corresponding to the industrial equipment of all production lines to obtain the correlation index of each industrial equipment model, and the industrial equipment corresponding to different production lines are connected and combined according to the connection relationship of the correlation map.

Furthermore, in S103, a correlation map of industrial equipment corresponding to each production line is drawn, specifically including:

For each production line, according to the corresponding set of industrial equipment of the production line, each industrial equipment is taken as the initial node, and the position coordinates and model of the corresponding industrial equipment are marked on the initial node, and the adjacent industrial equipment models are extracted, and the above adjacent industrial equipment is taken as the associated node, and the corresponding industrial equipment model is marked on the associated node, and the initial node is connected with the associated node. If the equipment models corresponding to the initial nodes are the same but the position coordinates are different, the initial nodes are merged and marked with the corresponding position marks, and so on, the above corresponding association maps are drawn for all industrial equipment;

The correlation maps corresponding to the industrial equipment of all production lines are integrated to obtain the correlation index of each industrial equipment model. The specific analysis process is as follows:

Based on the association map corresponding to each industrial equipment, the initial nodes corresponding to different production lines are extracted, and the initial nodes in the association map corresponding to each industrial equipment are merged according to the initial node merging steps, so as to obtain the association map corresponding to each industrial equipment in the production workshop; based on the association map corresponding to each industrial equipment in the production workshop, the association index G of each industrial equipment is calculated, and the specific formula of the association index G is: G=C/M, where C represents the number of types of connected association nodes when the corresponding industrial equipment is used as the initial node, and M represents the number of types of industrial equipment in the production workshop.

Further, step S200 includes:

S201. Obtain historical production data of the production workshop, and for each production line, divide the historical production data according to the industrial equipment to which it belongs, thereby obtaining a number of data segments, each of which corresponds to an industrial equipment; for each data segment, mark the time point corresponding to the above data segment according to the time point when the industrial equipment fails in the maintenance record, and filter out the time period corresponding to the above data segment according to the maintenance time period in the maintenance record; thereby obtaining a number of sub-data segments corresponding to the continuous time series;

S202. Based on the above sub-data segments, the load condition of each industrial equipment is evaluated to obtain the load index F of each industrial equipment of each production line, and the specific calculation formula of the load index F is:

F=[Σ _t∈[1,m] (Rt/R0)*Lt]/m,

Wherein, Rt represents the actual amount of production tasks completed in the t-th sub-data segment of the corresponding industrial equipment, t represents the sub-data segment number of the corresponding industrial equipment, m represents the number of sub-data segments of the corresponding industrial equipment, R0 represents the theoretical maximum amount of production tasks completed in the corresponding industrial equipment, and Lt represents the ratio of the actual operating time of the industrial equipment in the t-th sub-data segment of the corresponding industrial equipment to the total time of the t-th sub-data segment;

S203. Obtain the correlation index of each industrial equipment model, and correspond the load index of each industrial equipment of each production line with the correlation index of the corresponding industrial equipment model, thereby forming several reference data sets D, and the number of reference data sets D is equal to the number M of industrial equipment types in the production workshop.

Furthermore, step S300 includes:

S301. Obtain real-time production data of the production workshop, and for each production line, divide the real-time production data according to the industrial equipment to which it belongs, thereby obtaining several data segments; according to the above data segments as sub-data segments in S202, according to the calculation formula in S202, and m=1, calculate the real-time load index F1 of each industrial equipment of each production line;

S302. For each industrial equipment on each production line, obtain the current industrial equipment model, search in the reference data set D according to the current industrial equipment model, obtain the corresponding load index F, compare the relationship between the ratio of the real-time load index F1 and the above load index F and the threshold interval Q, and the threshold interval Q=(q1,q2), where q1 represents the left boundary of the threshold interval Q, and q2 represents the right boundary of the threshold interval Q; if (F-F1) belongs to the threshold interval Q, the current industrial equipment does not need maintenance; if (F-F1) does not belong to the threshold interval Q, the current industrial equipment needs maintenance.

For the left and right boundaries of the threshold interval Q, we have:

Since the calculation formula of the load index F is: F=[Σt∈[1,m](Rt/R0)*Lt]/m, it can be seen from the formula that the average value of (Rt/R0)*Lt corresponding to each sub-data segment is calculated, so the load index F belongs between the maximum and minimum values of (Rt/R0)*Lt, so the minimum value q1 in the threshold interval Q＞F-[(Rt/R0)*Lt]max, and the maximum value q2 in the threshold interval Q＜F-[(Rt/R0)*Lt]min.

Furthermore, step S400 includes:

S401. For the production line where the industrial equipment that needs maintenance is located, shut down the industrial equipment that currently needs maintenance, and send the location coordinates of the current industrial equipment to relevant personnel for maintenance and management by relevant personnel; obtain the current production line equipment number and update the corresponding production line industrial equipment set;

S402. Obtain the updated production line industrial equipment set, perform industrial equipment model similarity calculation based on the above production line industrial equipment set and the production line industrial equipment set corresponding to other production lines, extract the numbers of other production lines whose similarity calculation is equal to 1, input the above other production line numbers to relevant personnel, and obtain the real-time pending production task information of other production lines, and the relevant personnel assign the real-time pending production task information to the current production line;

S403. When all the real-time information on pending production tasks of other production lines is completed, if the industrial equipment that needs maintenance fails to work normally, obtain the industrial equipment set of other production lines; based on the industrial equipment set of other production lines, represent the location distribution of industrial equipment of other production lines, and thus obtain an industrial equipment location distribution map; analyze according to the industrial equipment location distribution map, if it is found that adjacent production lines can form a temporary production line, and the temporary production line is exactly the same as the industrial equipment model of the production line where the industrial equipment that needs maintenance is located, then the temporary production line will be output to relevant personnel, and the relevant personnel will perform real-time pending production task allocation.

An industrial equipment intelligent scheduling system based on adaptive control, the system includes: a data acquisition and processing module, an industrial equipment correlation index calculation module, a load situation evaluation and comparison module, a maintenance and scheduling decision module, and a maintenance management and execution module;

The data acquisition and processing module is responsible for acquiring the industrial equipment information and historical production data of all production lines in the production workshop, forming a set of industrial equipment for the production line, and conducting load assessment;

The industrial equipment association index calculation module is responsible for constructing the association map of industrial equipment and integrating the association maps corresponding to the industrial equipment of all production lines, and finally obtaining the association index of each industrial equipment model;

The load condition assessment and comparison module assesses the load condition of the industrial equipment of each production line, and matches the load condition assessment results with the correlation index of the industrial equipment model to form a comparison data set; as well as compares the real-time load index with the historical load index, and determines whether the industrial equipment needs maintenance;

The maintenance and scheduling decision module analyzes the production line where the industrial equipment that needs maintenance is located, and performs similarity calculation to determine the replaceable production line; when maintenance is required, real-time pending production task information is allocated to other production lines; and the industrial equipment set of other production lines is obtained, and the position distribution is represented, and it is determined whether the production line where the industrial equipment that needs maintenance is located can be replaced; according to the analysis of the industrial equipment location distribution, if adjacent production lines are found to form a temporary production line, so that the temporary production line and the industrial equipment model corresponding to the production line where the industrial equipment that needs maintenance is located are exactly the same, then the temporary production line is output to relevant personnel, and the relevant personnel perform real-time pending production task allocation;

The maintenance management and execution module is responsible for sending the location coordinates of the current industrial equipment to relevant personnel for maintenance management, and executing the corresponding real-time production tasks based on the judgment result of whether the temporary production line can replace the production line where the industrial equipment that needs maintenance is located.

Further, the data acquisition and processing module includes a data acquisition unit and a data processing unit;

The data acquisition unit is responsible for acquiring the industrial equipment information, historical production data and real-time production data of the production workshop; the data processing unit processes the acquired data, including the analysis, extraction and arrangement of historical data, as well as the parsing and processing of real-time data;

The industrial equipment correlation index calculation module includes an industrial equipment correlation map construction unit and a correlation index calculation unit;

The industrial equipment association map construction unit constructs an industrial equipment association map corresponding to each production line according to the industrial equipment set of the production line; the association index calculation unit calculates the association index of each industrial equipment model according to the industrial equipment association map.

Further, the load condition evaluation and comparison module includes a historical load condition evaluation unit, a real-time load condition evaluation unit, and a comparison data set construction unit;

The historical load condition evaluation unit evaluates the load condition of the historical production data and calculates the load index of each industrial equipment; the real-time load condition evaluation unit calculates the real-time load index of the industrial equipment of each production line based on the real-time production data; the reference data set construction unit matches the historical load condition evaluation results with the correlation index of the industrial equipment model to construct a reference data set.

Further, the maintenance and scheduling decision module includes a maintenance judgment unit and a scheduling decision unit;

The maintenance judgment unit determines whether the current industrial equipment needs maintenance based on the real-time load evaluation results and the reference data set; the scheduling decision unit performs maintenance management on the industrial equipment that needs maintenance, shuts down the equipment that needs maintenance, and updates the current production line industrial equipment set to determine whether the current production line can execute the pending production tasks of other production lines, and whether other production lines can execute the pending production tasks of the current production line after combination, and outputs the scheduling decision result based on the judgment result; and obtains the industrial equipment set of other production lines, represents the location distribution, and determines whether the production line where the industrial equipment that needs maintenance is located can be replaced; analyzes the industrial equipment location distribution, and if adjacent production lines are found to form a temporary production line, so that the temporary production line and the corresponding industrial equipment model of the production line where the industrial equipment that needs maintenance is located are exactly the same, then the temporary production line is output to relevant personnel, and the relevant personnel perform real-time pending production task allocation;

The maintenance management and execution module includes a maintenance management unit and a scheduling execution unit;

The maintenance management unit is responsible for managing maintenance tasks, including notifying relevant personnel to perform maintenance and managing maintenance records; the scheduling execution unit performs corresponding scheduling operations based on the scheduling decision results.

Compared with the prior art, the beneficial effects achieved by the present invention are:

By constructing a set of industrial equipment for each production line and calculating the correlation index of industrial equipment models based on the correlation map of industrial equipment, the correlation relationship between industrial equipment is taken into account, which helps to better understand the dependence and impact between industrial equipment; the load condition of industrial equipment on each production line is evaluated, and the load index of industrial equipment is evaluated through historical production data and real-time production data, which helps to timely discover the load condition of industrial equipment and predict potential failure risks; based on the real-time production data and load condition evaluation results, it can be determined whether the current industrial equipment needs maintenance, and the industrial equipment that needs maintenance can be shut down and maintained in time, and intelligent scheduling decisions can be made at the same time, and the remaining production line industrial equipment can be compared with other production lines to determine whether there is a replacement production line to ensure the smooth execution of production tasks; in the case of complex production lines, temporary production lines that can share resources can enable production lines to collaborate with each other, share equipment and human resources, greatly reducing the time for relevant personnel to find temporary production lines, and further improving the production efficiency and resource utilization of the entire factory; through timely maintenance of faulty industrial equipment, intelligent scheduling of replacement production lines and other measures, the production line downtime can be minimized, production efficiency can be improved, production costs can be reduced, thereby enhancing the competitiveness and economic benefits of the factory.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

FIG1 is a schematic diagram of a module of an industrial equipment intelligent scheduling system based on adaptive control according to the present invention.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Please refer to Figure 1, the present invention provides a technical solution:

An industrial equipment intelligent scheduling system based on adaptive control, the system includes: a data acquisition and processing module, an industrial equipment correlation index calculation module, a load situation evaluation and comparison module, a maintenance and scheduling decision module, and a maintenance management and execution module;

The data acquisition and processing module is responsible for acquiring the industrial equipment information and historical production data of all production lines in the production workshop, forming a set of industrial equipment for the production line, and conducting load assessment;

The industrial equipment association index calculation module is responsible for constructing the association map of industrial equipment and integrating the association maps corresponding to the industrial equipment of all production lines, and finally obtaining the association index of each industrial equipment model;

The load condition assessment and comparison module assesses the load condition of the industrial equipment of each production line, and matches the load condition assessment results with the correlation index of the industrial equipment model to form a comparison data set; as well as compares the real-time load index with the historical load index, and determines whether the industrial equipment needs maintenance;

The maintenance and scheduling decision module analyzes the production line where the industrial equipment that needs maintenance is located, and performs similarity calculation to determine the replaceable production line; when maintenance is required, real-time pending production task information is allocated to other production lines; and the industrial equipment set of other production lines is obtained, and the position distribution is represented, and it is determined whether the production line where the industrial equipment that needs maintenance is located can be replaced; according to the analysis of the industrial equipment location distribution, if adjacent production lines are found to form a temporary production line, so that the temporary production line and the industrial equipment model corresponding to the production line where the industrial equipment that needs maintenance is located are exactly the same, then the temporary production line is output to relevant personnel, and the relevant personnel perform real-time pending production task allocation;

The maintenance management and execution module is responsible for sending the location coordinates of the current industrial equipment to relevant personnel for maintenance management, and executing the corresponding real-time production tasks based on the judgment results of whether two adjacent production lines can replace the production line where the industrial equipment that needs maintenance is located.

The data acquisition and processing module includes a data acquisition unit and a data processing unit;

The data acquisition unit is responsible for acquiring the industrial equipment information, historical production data and real-time production data of the production workshop; the data processing unit processes the acquired data, including the analysis, extraction and arrangement of historical data, as well as the parsing and processing of real-time data;

The industrial equipment correlation index calculation module includes an industrial equipment correlation map construction unit and a correlation index calculation unit;

The industrial equipment association map construction unit constructs an industrial equipment association map corresponding to each production line according to the industrial equipment set of the production line; the association index calculation unit calculates the association index of each industrial equipment model according to the industrial equipment association map.

The load condition evaluation and comparison module includes a historical load condition evaluation unit, a real-time load condition evaluation unit, and a comparison data set construction unit;

The historical load condition evaluation unit evaluates the load condition of the historical production data and calculates the load index of each industrial equipment; the real-time load condition evaluation unit calculates the real-time load index of the industrial equipment of each production line based on the real-time production data; the reference data set construction unit matches the historical load condition evaluation results with the correlation index of the industrial equipment model to construct a reference data set.

The maintenance and scheduling decision module includes a maintenance judgment unit and a scheduling decision unit;

The maintenance judgment unit determines whether the current industrial equipment needs maintenance based on the real-time load evaluation results and the reference data set; the scheduling decision unit performs maintenance management on the industrial equipment that needs maintenance, shuts down the equipment that needs maintenance, and updates the current production line industrial equipment set to determine whether the current production line can execute the pending production tasks of other production lines, and whether other production lines can execute the pending production tasks of the current production line after combination, and outputs the scheduling decision result based on the judgment result; and obtains the industrial equipment set of other production lines, represents the location distribution, and determines whether the production line where the industrial equipment that needs maintenance is located can be replaced; analyzes the industrial equipment location distribution, and if adjacent production lines are found to form a temporary production line, so that the temporary production line and the corresponding industrial equipment model of the production line where the industrial equipment that needs maintenance is located are exactly the same, then the temporary production line is output to relevant personnel, and the relevant personnel perform real-time pending production task allocation;

The maintenance management and execution module includes a maintenance management unit and a scheduling execution unit;

The maintenance management unit is responsible for managing maintenance tasks, including notifying relevant personnel to perform maintenance and managing maintenance records; the scheduling execution unit performs corresponding scheduling operations based on the scheduling decision results.

An industrial equipment intelligent scheduling method based on adaptive control comprises the following steps:

Step S100. Obtain the industrial equipment information and corresponding historical production data of all production lines in the production workshop to form a production line industrial equipment set; based on the production line industrial equipment set, obtain the corresponding industrial equipment information of each production line, thereby obtaining the correlation index of the industrial equipment model;

Step S200. Based on the historical production data of the production workshop, the load condition of the industrial equipment of each production line is evaluated; the load condition evaluation result of the industrial equipment of each production line is matched with the correlation index of the industrial equipment model, thereby forming a control data set;

Step S300. Obtain the real-time production data of the production workshop, and calculate the real-time load evaluation of the industrial equipment of each production line based on the real-time production data of the production workshop; for each production line, determine whether the current industrial equipment needs maintenance based on the real-time load evaluation results of the industrial equipment and in combination with the reference data set;

Step S400. For the production line where the industrial equipment that needs maintenance is located, shut down the industrial equipment that currently needs maintenance, compare the remaining industrial equipment on the production line with the industrial equipment on other production lines, and determine whether there is a production line composed of the same industrial equipment; obtain real-time information on pending production tasks. If other production lines have completed all real-time pending production tasks, determine whether there are other production lines that form a temporary production line to replace the production line where the industrial equipment that needs maintenance is located, and make intelligent scheduling decisions based on the judgment results.

Step S100 includes:

S101. The industrial equipment information includes the industrial equipment number and the industrial equipment distribution location, and the industrial equipment number includes the industrial equipment model; the historical production data refers to the production data of the production workshop in the past period of time, including the production task execution data, operation data and maintenance records of each industrial equipment;

S102. For each production line in the production workshop, extract the corresponding industrial equipment number, and set a position coordinate according to the corresponding industrial equipment distribution position, and correspond the position coordinate with the industrial equipment number, so as to form a production line industrial equipment set Ai, and Ai={ai1,ai2,...,ain}, where i represents the production line number, ai1 represents the industrial equipment number with the position coordinate (i,1), and (i,1) represents the position coordinate of the industrial equipment in the i-th row and the first column; ai2 represents the industrial equipment number with the position coordinate (i,2), and so on, ain represents the industrial equipment number with the position coordinate (i,n), and n represents the number of industrial equipment constituting the production line;

S103. Draw a correlation map of the industrial equipment corresponding to each production line based on the set of production line industrial equipment corresponding to each production line, wherein each industrial equipment corresponds to one correlation map; integrate the correlation maps corresponding to the industrial equipment of all production lines to obtain the correlation index of each industrial equipment model, and the industrial equipment corresponding to different production lines are connected and combined according to the connection relationship of the correlation map.

In S103, a correlation map of industrial equipment corresponding to each production line is drawn, specifically including:

For each production line, according to the corresponding set of industrial equipment of the production line, each industrial equipment is taken as the initial node, and the position coordinates and model of the corresponding industrial equipment are marked on the initial node, and the adjacent industrial equipment models are extracted, and the above adjacent industrial equipment is taken as the associated node, and the corresponding industrial equipment model is marked on the associated node, and the initial node is connected with the associated node. If the equipment models corresponding to the initial nodes are the same but the position coordinates are different, the initial nodes are merged and marked with the corresponding position marks, and so on, the above corresponding association maps are drawn for all industrial equipment;

The correlation maps corresponding to the industrial equipment of all production lines are integrated to obtain the correlation index of each industrial equipment model. The specific analysis process is as follows:

Based on the association map corresponding to each industrial equipment, the initial nodes corresponding to different production lines are extracted, and the initial nodes in the association map corresponding to each industrial equipment are merged according to the initial node merging steps, so as to obtain the association map corresponding to each industrial equipment in the production workshop; based on the association map corresponding to each industrial equipment in the production workshop, the association index G of each industrial equipment is calculated, and the specific formula of the association index G is: G=C/M, where C represents the number of types of connected association nodes when the corresponding industrial equipment is used as the initial node, and M represents the number of types of industrial equipment in the production workshop.

In this embodiment, it is assumed that there are three production lines. The industrial equipment model of each production line is obtained according to the corresponding production line industrial equipment set, which is:

Production line 1: a, b, d, c, b;

Production line 2: a, b, c, b;

Production line 3: a, b, d, c;

Take production line 1 as an example.

Initial node (a)(1,1)→b; a→initial node (b)(1,2)→d;

b→initial node (d)(1,3)→c; c→initial node (b)(1,4);

Since the initial node (b) appears twice and the corresponding device models are the same but the position coordinates are different, the initial nodes are merged and marked with the corresponding position marks, so the initial node (b) is merged into: a→initial node (b) (1,2) (1,4)→d and c→initial node (b) (1,4).

By analogy, the correlation index of each industrial equipment model is calculated. Taking industrial equipment model a as an example, since industrial equipment model a is connected to industrial equipment model b, the correlation index G(a)=1/4=0.25.

Step S200 includes:

S201. Obtain historical production data of the production workshop, and for each production line, divide the historical production data according to the industrial equipment to which it belongs, thereby obtaining a number of data segments, each of which corresponds to an industrial equipment; for each data segment, mark the time point corresponding to the above data segment according to the time point when the industrial equipment fails in the maintenance record, and filter out the time period corresponding to the above data segment according to the maintenance time period in the maintenance record; thereby obtaining a number of sub-data segments corresponding to the continuous time series;

S202. Based on the above sub-data segments, the load condition of each industrial equipment is evaluated to obtain the load index F of each industrial equipment of each production line, and the specific calculation formula of the load index F is:

F=[Σ _t∈[1,m] (Rt/R0)*Lt]/m,

Wherein, Rt represents the actual amount of production tasks completed in the t-th sub-data segment of the corresponding industrial equipment, t represents the sub-data segment number of the corresponding industrial equipment, m represents the number of sub-data segments of the corresponding industrial equipment, R0 represents the theoretical maximum amount of production tasks completed in the corresponding industrial equipment, and Lt represents the ratio of the actual operating time of the industrial equipment in the t-th sub-data segment of the corresponding industrial equipment to the total time of the t-th sub-data segment;

S203. Obtain the correlation index of each industrial equipment model, and correspond the load index of each industrial equipment of each production line with the correlation index of the corresponding industrial equipment model, thereby forming several reference data sets D, and the number of reference data sets D is equal to the number M of industrial equipment types in the production workshop.

In this embodiment, taking industrial equipment model a as an example, it is known that the correlation index G(a)=1/4=0.25, so the corresponding reference data set D is expressed as: D[G(a)=0.25]={F1,F2,F3}, where F1 represents the load index of industrial equipment model a in the first production line, and so on.

Step S300 includes:

S301. Obtain real-time production data of the production workshop, and for each production line, divide the real-time production data according to the industrial equipment to which it belongs, thereby obtaining several data segments; according to the above data segments as sub-data segments in S202, according to the calculation formula in S202, and m=1, calculate the real-time load index F1 of each industrial equipment of each production line;

S302. For each industrial equipment on each production line, obtain the current industrial equipment model, search in the reference data set D according to the current industrial equipment model, obtain the corresponding load index F, compare the relationship between the ratio of the real-time load index F1 and the above load index F and the threshold interval Q, and the threshold interval Q=(q1,q2), where q1 represents the left boundary of the threshold interval Q, and q2 represents the right boundary of the threshold interval Q; if (F-F1) belongs to the threshold interval Q, the current industrial equipment does not need maintenance; if (F-F1) does not belong to the threshold interval Q, the current industrial equipment needs maintenance.

For the left and right boundaries of the threshold interval Q, we have:

Since the calculation formula of the load index F is: F=[Σt∈[1,m](Rt/R0)*Lt]/m, it can be seen from the formula that the average value of (Rt/R0)*Lt corresponding to each sub-data segment is calculated, so the load index F belongs between the maximum and minimum values of (Rt/R0)*Lt, so the minimum value q1 in the threshold interval Q＞F-[(Rt/R0)*Lt]max, and the maximum value q2 in the threshold interval Q＜F-[(Rt/R0)*Lt]min.

Step S400 includes:

S401. For the production line where the industrial equipment that needs maintenance is located, shut down the industrial equipment that currently needs maintenance, and send the location coordinates of the current industrial equipment to relevant personnel for maintenance and management by relevant personnel; obtain the current production line equipment number and update the corresponding production line industrial equipment set;

S402. Obtain the updated production line industrial equipment set, perform industrial equipment model similarity calculation based on the above production line industrial equipment set and the production line industrial equipment set corresponding to other production lines, extract the numbers of other production lines whose similarity calculation is equal to 1, input the above other production line numbers to relevant personnel, and obtain the real-time pending production task information of other production lines, and the relevant personnel assign the real-time pending production task information to the current production line;

S403. When all the real-time information on pending production tasks of other production lines is completed, if the industrial equipment that needs maintenance fails to work normally, obtain the industrial equipment set of other production lines; based on the industrial equipment set of other production lines, represent the location distribution of industrial equipment of other production lines, and thus obtain an industrial equipment location distribution map; analyze according to the industrial equipment location distribution map, if it is found that adjacent production lines can form a temporary production line, and the temporary production line is exactly the same as the industrial equipment model of the production line where the industrial equipment that needs maintenance is located, then the temporary production line will be output to relevant personnel, and the relevant personnel will perform real-time pending production task allocation.

By shutting down industrial equipment that needs maintenance and sending its location coordinates to relevant personnel, the industrial equipment can be maintained and managed in a timely manner, reducing the risk of equipment failure and improving the reliability and stability of the production line. Based on the calculation of the similarity of industrial equipment models, the real-time pending production task information of other production lines is assigned to the current production line, so that production tasks can be flexibly scheduled between different production lines, maximizing the utilization rate of the production line and improving production efficiency. Through the analysis of the location distribution of industrial equipment, temporary production lines that can share resources are found, so that production lines can collaborate with each other, share equipment and human resources, and further improve the production efficiency and resource utilization of the entire factory. By executing real-time pending production tasks on temporary production lines that can replace the maintenance production line, the downtime of the production line can be reduced during maintenance, ensuring production continuity and minimizing production losses.

In this embodiment, it is assumed that there are three production lines. The industrial equipment model of each production line is obtained according to the corresponding production line industrial equipment set, which is:

Production line 1: a, b, d, c, b;

Production line 2: a, b, c, b;

Production line 3: a, b, d, c;

Assuming that industrial equipment model d in production line 1 needs maintenance, the industrial equipment that currently needs maintenance is shut down, and the location coordinates of industrial equipment model d are output to relevant personnel for maintenance management; the current production line equipment number is obtained, and the corresponding production line industrial equipment set is updated. Therefore, the industrial equipment models in the production line industrial equipment set of the current production line are: a, b, d, c;

Since the number of the other production line with the current similarity calculation equal to 1 is production line 2, production line 2 is input to the relevant personnel, who then judge whether the current production line can execute the production tasks of production line 2. If the judgment result is that the production tasks of other production lines can be executed, the real-time pending production task information of production line 2 is obtained, and the real-time pending production task information is assigned to the current production line;

Assuming that all the real-time production tasks to be completed on production lines 2 and 3 have been completed, and the industrial equipment model d on production line 1 still cannot work normally, then based on the industrial equipment set of other production lines, the location distribution of the industrial equipment on other production lines is represented, thereby obtaining an industrial equipment location distribution map; therefore, it can be obtained that production line 1 can be obtained by combining the industrial equipment on production lines 2 and 3, and therefore the temporary production line composed of production lines 2 and 3 is sent to relevant personnel, who will then allocate the real-time production tasks to be completed; in actual applications, there may be more than one temporary production line, and the present invention can output all temporary production lines to relevant personnel as a reference, and the specific scheduling method is determined by relevant personnel, thereby greatly reducing the time for relevant personnel to find the temporary production line, maximizing the utilization rate of the production line, and improving production efficiency.

It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims (7)

1. An intelligent dispatching method for industrial equipment based on self-adaptive control is characterized by comprising the following steps: the method comprises the following steps:

S100, acquiring industrial equipment information and corresponding historical production data of all production lines of a production workshop to form a production line industrial equipment set; based on the industrial equipment set of the production lines, acquiring corresponding industrial equipment information of each production line, thereby obtaining an association index of the industrial equipment model;

The step S100 includes:

S101, the industrial equipment information comprises industrial equipment numbers and industrial equipment distribution positions, and the industrial equipment numbers comprise industrial equipment models; the historical production data refers to production data in a past period of time of a production workshop, and comprises production task execution data, operation data and maintenance records of each industrial equipment;

S102, for each production line of a production workshop, extracting a corresponding industrial equipment number, setting a position coordinate according to the corresponding industrial equipment distribution position, and corresponding the position coordinate to the industrial equipment number to form a production line industrial equipment set Ai, wherein ai= { Ai1, ai2, ain }, i represents the production line number, ai1 represents the industrial equipment number with the position coordinate of (i, 1), and (i, 1) represents the position coordinate of industrial equipment with the i-th row and the 1-th column; ai2 represents the industrial equipment number with the position coordinates of (i, 2), and so on, ain represents the industrial equipment number with the position coordinates of (i, n), and n represents the number of industrial equipment constituting the production line;

s103, according to the industrial equipment set of the production line corresponding to each production line, drawing a correlation map of the industrial equipment corresponding to each production line, wherein each industrial equipment corresponds to one correlation map; integrating the association graphs corresponding to the industrial equipment of all the production lines so as to obtain association indexes of each industrial equipment model, and connecting and combining the industrial equipment corresponding to different production lines according to the connection relation of the association graphs;

In S103, drawing a correlation map of the industrial equipment corresponding to each production line, which specifically includes:

For each production line, according to the corresponding industrial equipment set of the production line, taking each industrial equipment as an initial node, marking the position coordinates and the model of the corresponding industrial equipment on the initial node, extracting the model of the industrial equipment adjacent to the initial node, taking the adjacent industrial equipment as an associated node, marking the model of the corresponding industrial equipment on the associated node, connecting the initial node with the associated node, merging the initial nodes if the equipment models corresponding to the initial nodes are the same but the position coordinates are different, marking the corresponding position marks, and so on, and drawing the corresponding associated map for all the industrial equipment;

The association graphs corresponding to the industrial equipment of all production lines are integrated, so that the association index of each industrial equipment model is obtained, and the specific analysis process is as follows:

Based on the association graphs corresponding to each industrial equipment, extracting initial nodes corresponding to different production lines, and merging according to the initial node merging step in the association graphs corresponding to each industrial equipment, so as to obtain the association graph corresponding to each industrial equipment in a production workshop; based on the corresponding association map of each industrial equipment in the production workshop, calculating an association index G of each industrial equipment, wherein the specific formula of the association index G is as follows: g=c/M, where C represents the number of connected association node types when the corresponding industrial device is used as an initial node, and M represents the number of industrial device types in the production plant;

s200, carrying out load condition evaluation on industrial equipment of each production line according to historical production data of a production workshop; the load condition evaluation result of the industrial equipment of each production line is corresponding to the association index of the industrial equipment model, so that a comparison data set is formed;

S300, acquiring real-time production data of a production workshop, and calculating real-time load condition evaluation of industrial equipment of each production line according to the real-time production data of the production workshop; for each production line, judging whether the current industrial equipment needs to be maintained or not according to the real-time load condition evaluation result of the industrial equipment and by combining a comparison data set;

S400, closing industrial equipment which needs to be maintained at present for a production line where the industrial equipment which needs to be maintained is located, comparing the industrial equipment of the remaining production line with industrial equipment of other production lines, and judging whether production lines consisting of the same industrial equipment exist or not; and acquiring real-time task information to be produced, judging whether a temporary production line formed by other production lines is available to replace a production line where industrial equipment to be maintained is located if all the real-time tasks to be produced are completed by the other production lines, and performing intelligent scheduling decision according to a judgment result.

2. The intelligent dispatching method for the industrial equipment based on the adaptive control according to claim 1, wherein the intelligent dispatching method is characterized by comprising the following steps of: the step S200 includes:

s201, acquiring historical production data of a production workshop, dividing the historical production data according to industrial equipment of each production line so as to obtain a plurality of data segments, wherein each data segment corresponds to one industrial equipment; for each data segment, marking the corresponding time point of the data segment according to the time point of the fault of the industrial equipment in the maintenance record, and screening out the corresponding time segment of the data segment according to the maintenance time segment in the maintenance record; thereby obtaining a plurality of sub-data segments corresponding to the continuous time sequences;

S202, carrying out load condition evaluation on each industrial equipment based on the sub-data segments, so as to obtain a load index F of each industrial equipment of each production line, wherein the specific calculation formula of the load index F is as follows:

F=[Σ_t∈[1,m](Rt/R0)*Lt]/m，

Wherein Rt represents the execution amount of the actual completion production task in the t-th sub-data section of the corresponding industrial equipment, t represents the number of the sub-data section of the corresponding industrial equipment, m represents the number of the sub-data section of the corresponding industrial equipment, R0 represents the theoretical maximum execution amount of the completion production task of the corresponding industrial equipment, and Lt represents the ratio of the actual running time of the industrial equipment in the t-th sub-data section of the corresponding industrial equipment to the total time of the t-th sub-data section;

s203, obtaining an association index of each industrial equipment model, and corresponding the load index of each industrial equipment of each production line to the association index of the corresponding industrial equipment model, so that a plurality of comparison data sets D are formed, and the number of the comparison data sets D is equal to the number M of industrial equipment types of a production workshop.

3. The intelligent dispatching method for the industrial equipment based on the adaptive control according to claim 2, wherein the intelligent dispatching method is characterized by comprising the following steps of: the step S300 includes:

S301, acquiring real-time production data of a production workshop, and dividing the real-time production data according to industrial equipment of each production line so as to obtain a plurality of data segments; according to the data segment as the sub-data segment in S202, calculating a real-time load index F1 of each industrial equipment of each production line according to the calculation formula in S202, wherein m=1;

S302, for each industrial equipment of each production line, acquiring a current industrial equipment model, searching in a comparison data set D according to the current industrial equipment model to obtain a corresponding load index F, and comparing the relation between the ratio of the real-time load index F1 and the load index F and a threshold interval Q, wherein the threshold interval Q= (Q1, Q2), Q1 represents the left boundary of the threshold interval Q, and Q2 represents the right boundary of the threshold interval Q; if (F-F1) belongs to the threshold value interval Q, the current industrial equipment does not need maintenance; if (F-F1) does not belong to the threshold interval Q, maintenance is required for the current industrial equipment.

4. An intelligent dispatching method for industrial equipment based on self-adaptive control as claimed in claim 3, wherein: the step S400 includes:

S401, closing industrial equipment which needs to be maintained currently for a production line where the industrial equipment which needs to be maintained is located, and sending the position coordinates of the current industrial equipment to related personnel, wherein the related personnel perform maintenance management; acquiring the equipment number of the current production line, and updating the corresponding industrial equipment set of the production line;

S402, acquiring an updated production line industrial equipment set, performing industrial equipment model similarity calculation based on the production line industrial equipment set corresponding to other production lines, extracting other production line numbers with similarity calculation equal to 1, inputting the other production line numbers to related personnel, acquiring real-time task information to be produced of the other production lines, and distributing the real-time task information to be produced to the current production line by the related personnel;

S403, after the real-time production task information of other production lines is completely finished, if the industrial equipment to be maintained fails to work normally, acquiring an industrial equipment set of the other production lines; based on the industrial equipment collection of other production lines, carrying out industrial equipment position distribution representation of other production lines so as to obtain an industrial equipment position distribution diagram; and analyzing according to the position distribution diagram of the industrial equipment, and if the adjacent production lines are found to form a temporary production line, so that the temporary production line is completely the same as the corresponding industrial equipment model of the production line of the industrial equipment to be maintained, outputting the temporary production line to related personnel, and distributing the tasks to be produced in real time by the related personnel.

5. An industrial equipment intelligent scheduling system based on self-adaptive control, which is applied to the industrial equipment intelligent scheduling method based on self-adaptive control as set forth in any one of claims 1-4, and is characterized in that: the system comprises: the system comprises a data acquisition and processing module, an industrial equipment association index calculation module, a load condition evaluation and comparison module, a maintenance and scheduling decision module and a maintenance management and execution module;

the data acquisition and processing module is responsible for acquiring industrial equipment information and historical production data of all production lines of a production workshop, forming a production line industrial equipment set and carrying out load condition evaluation;

The industrial equipment association index calculation module is responsible for constructing association graphs of industrial equipment, integrating the association graphs corresponding to the industrial equipment of all production lines, and finally obtaining association indexes of each industrial equipment model;

The load condition evaluation and comparison module evaluates the load condition of the industrial equipment of each production line, and corresponds the load condition evaluation result to the association index of the model of the industrial equipment to form a comparison data set; comparing the real-time load index with the historical load index, and judging whether the industrial equipment needs maintenance or not;

The maintenance and scheduling decision module analyzes the production line of the industrial equipment to be maintained and calculates the similarity to determine an alternative production line; when maintenance is needed, distributing the real-time task information to be produced to other production lines; acquiring an industrial equipment set of other production lines, carrying out position distribution representation, and judging whether the production line of the industrial equipment needing maintenance can be replaced; analyzing according to the position distribution of the industrial equipment, if adjacent production lines are found to form a temporary production line, so that the temporary production line is identical to the corresponding industrial equipment model of the production line of the industrial equipment to be maintained, outputting the temporary production line to related personnel, and distributing real-time production task waiting for the related personnel;

The maintenance management and execution module is responsible for sending the position coordinates of the current industrial equipment to related personnel for maintenance management, and executing corresponding real-time production waiting tasks according to the judgment result of whether the temporary production line can replace the production line where the industrial equipment to be maintained is located;

the data acquisition and processing module comprises a data acquisition unit and a data processing unit;

the data acquisition unit is in charge of acquiring industrial equipment information, historical production data and real-time production data of a production workshop; the data processing unit processes the acquired data, including analysis, extraction and arrangement of historical data and analysis and processing of real-time data;

The industrial equipment association index calculation module comprises an industrial equipment association graph construction unit and an association index calculation unit;

The industrial equipment association map construction unit constructs an industrial equipment association map corresponding to each production line according to the industrial equipment collection of the production lines; the association index calculating unit calculates the association index of each industrial equipment model according to the industrial equipment association map.

6. The intelligent dispatching system for industrial equipment based on self-adaptive control as claimed in claim 5, wherein: the load condition evaluation and comparison module comprises a historical load condition evaluation unit, a real-time load condition evaluation unit and a comparison data set construction unit;

The historical load condition evaluation unit evaluates the load condition of the historical production data and calculates the load index of each industrial equipment; the real-time load condition evaluation unit calculates real-time load indexes of industrial equipment of each production line according to the real-time production data; and the control data set construction unit corresponds the historical load condition evaluation result to the association index of the industrial equipment model to construct a control data set.

7. The intelligent dispatching system for industrial equipment based on self-adaptive control as claimed in claim 5, wherein: the maintenance and scheduling decision module comprises a maintenance judging unit and a scheduling decision unit;

The maintenance judging unit judges whether the current industrial equipment needs maintenance or not according to the real-time load condition evaluation result and the comparison data set; the scheduling decision unit performs maintenance management on industrial equipment to be maintained, closes the equipment to be maintained, updates the industrial equipment set of the current production line, judges whether the current production line can execute the tasks to be produced of other production lines and whether the other production lines can execute the tasks to be produced of the current production line after combination, and outputs scheduling decision results according to the judgment results; acquiring an industrial equipment set of other production lines, carrying out position distribution representation, and judging whether the production line of the industrial equipment needing maintenance can be replaced; analyzing according to the position distribution of the industrial equipment, if adjacent production lines are found to form a temporary production line, so that the temporary production line is identical to the corresponding industrial equipment model of the production line of the industrial equipment to be maintained, outputting the temporary production line to related personnel, and distributing real-time production task waiting for the related personnel;

The maintenance management and execution module comprises a maintenance management unit and a scheduling execution unit;

the maintenance management unit is responsible for managing maintenance tasks, including informing related personnel to carry out maintenance and management of maintenance records; and the scheduling execution unit executes corresponding scheduling operation according to the scheduling decision result.